Realtime agent stuck in a conversational loop after 0.1.0 update

API
1

Hello OpenAI community :

We are facing an issue related to the Realtime Agent configuration using the Agents SDK where after the latest update (0.1.0), our Realtime Agent just runs into a loop, here’s a conversation example :

Agent : Good morning! Before starting, are you an individual or a professional?
Agent : Good morning! Before starting, are you an individual or a professional?
User : individual
Agent : Good morning! Before starting, are you an individual or a professional?
User : individual…
Agent: Good, how may I help you ?
User : I need … { user clearly asks for a specific need }
Agent : Good, how may I help you ?
User : I need … { user clearly asks for a specific need again }
User : { agent doesn’t respond so user asks for need again in a simple wording }
User : { agent doesn’t respond again so user asks for need again in a simple wording and then ends the conversation }

As you may conclude, the implementation is very poorly handled, the agent not only repeats itself for no apparent reason and also sometimes doesn’t event answer.

We thought the problem might come from the prompt, which we have altered on many iterations but the issue doesn’t seem to stem from here since this problem is also observed on many very different prompts. Here’s the example of the previous conversation prompt used for the agent (the prompt is translated from French, apologies for possible confusion in wording).

As a result, we have rewinded to the previous 0.17.0 version, which seem to work okay [although it’s not really good neither in terms of quality of speech and intelligence compared to the experience we have access to in the playground or the app strangely… (e.g., lack of emotions in the voice, “fake breathing”, etc.")].
Additionally, the issue seems to persist even on 0.17.0 only when we select the newly released gpt-realtime model.

We’re out of options on how to fix this issue, hence why I’m turning towards the Agent SDK community.
Finally, our very simple code implementation of the agent can be found in the openai.ts file.

Does anyone else face a similar issue ? If so, have you managed to resolve it ? How ?
We’ll enormously appreciate any kind of help on this matter since we’re desperately out of possibilities…

Do not hesitate to let me know if any additional code resources are needed for better understanding of the matter.

2

I’m running into this exact same issue. The agent just continually repeats itself and doesn’t seem to process or respond to user input intermittently:
Agent: I see you’re calling from . Would you like to use this as your contact number?User: Yes.
Agent: I see you’re calling from . Would you like to use this as your contact number?
User: Yes.
Agent: I see you’re calling from . Would you like to use this as your contact number?
…

As a user, I would often have to say “yes” multiple times within the same turn before the agent processes the response. Even then, the response is broken. At this point I don’t know that we’d be able to move forward with the project, because the agent is just unbelievably brittle.

@gregory_buffard - Were you able to diagnose and resolve the issue?